摘要
以汽车手套箱翘曲问题的解决为例,针对产品翘曲变形问题,运用CAE有限元分析对其注塑工艺进行了仿真分析,首先优化并确定了产品的浇注方案,进一步的保压、冷却及翘曲分析表明,保压和冷却能得到有效保证,但翘曲变形大为产品注塑的主要质量问题。依据CAE分析的产品翘曲的分离因素结果,运用GRA灰色关联分析法并结合RBF神经网络对其工艺影响因素进行权重取值,调整后的GRA-RBF神经网络对工艺参数因素水平与翘曲变形量之间的关系具有较为准确的预测,依据此神经网络模型,得到产品注塑的优化工艺参数,获得了高质量的注塑产品,降低模具制造成本,有效缩短了模具生产周期。
In order to solve the problem of warping the glove box of a vehicle as an example, aiming at the problem of warping deformation, using CAE finite element analysis to simulate the injection molding process, first optimize and determine the pouring scheme of products, through further pressure, cooling and warpage analysis shows that the packing and cooling can be effectively guaranteed, but the warp the main quality problems for large deformation of injection molding products. On the basis of the results of separation factors CAE analysis of the warp of the product, using the GRA method of grey correlation analysis and RBF neural network combined with the factors affecting the process value, after adjusting the process parameters of GRARBF neural network on warping factor levels and the relationship between the deformation has a more accurate prediction, on the basis of the neural network model, to obtain the optimization of process parameters of injection molding products and the plastic products of high quality, reduce manufacturing cost and shorten the manufacturing cycle of the mould.
出处
《塑料科技》
CAS
北大核心
2017年第9期79-84,共6页
Plastics Science and Technology
基金
广西教育厅科研课题(KY2015YB479)
2015年度广西职业教育教改项目(桂教职成(2015))
关键词
CAE仿真
翘曲变形
灰度关联法
神经网络
优化
CAE simulation
Warping deformation
Gray correlation method
Neural network
Optimization
作者简介
马振锋（1965-），男，壮族，广西百色人，讲师，从事汽车电气设备及汽车电控技术方向研究。
通讯联系人
